Week 8 Journal

Weekly Report: September 9th - 15th

Reflection

This week I have been continuing my ongoing research and diving into the uncanny, utilised the latest advanced methods for image generation and utilised a workaround that uses optimization techniques typically used in LLM's to be able to run thelarge DEV-Flux model on my gaming laptop with limited gpu space.

Through this praactice i started exploring ideas of using these assets in real sculptural pieces, animating them etc.

I continued my reading of Communicology by Vilem Flusser and read Art in the age of mechanical reproduction by .....{insert author here}.... I also watched Synechdoche new york; which famously uses the ideas of jean beaudrillard as a key part of the narrative;

these pieces have been enhancing my media literacy and understandings of interpretations of impacts of the systems and the current prevalent reward mechanisms and content based feed system or ideology / behavioural system.

RESEARCH

FLUX - GGUFF Models and learnt how to use comfyui - specifically youtube tutorials and documentation.

I've found a way to speed up my data collection project using a Python script download_reels.py) that uses Instaloader. I'm now able to collect Instagram Reels and store them locally. This new method allows me to keep a list of good videos on my mobile phone, send them to myself, and clear the list each time, saving me from downloading individual files.

Insert Instaloader Github Project Link

COMFY-UI - FLUXX - GGUFF

This week i began researching how to use the latest ai model FLUX; I had been seeing some fairly wild outcomes across social media.
I began by watching several youtube videos on this topic and realised I had to install comfy ui; previously I had used automatic1111 running sdxl locally with some additional more advanced techniques such as inpainting addons etc but had found the node based input system of comfyui to be a bit daunting.

After installing Comfyui I had to find a workaround for running the latest flux model on low vram as the recommended minimum is 12gb and my laptop only as 6gb. I found someone had made use of an optimisation or memory caching technique typically used for languae models on lower end devices that had been adapted to work with the flux image generation system. After downloading this I began to test out the two different models. Flux Dev and Flux Schnell. Schnell is a model that has been trained from the larger dataset on its output images and therefor is more condensed and faster. However I was seeing better more coherent results from the larger DEV model.

Below are the comparisons between the two models of some generations, i believe you will see what I mean.

Flux experiments -

FLUX DEV

ComfyUI_temp_rsucy_00008_.png
ComfyUI_temp_rsucy_00009_.png

ComfyUI_temp_spelr_00003_.png

FLUX SCHNELL

ComfyUI_00091_.png
ComfyUI_00107_.png ComfyUI_00109_.png ComfyUI_00111_.png ComfyUI_00112_.png

Thursday Night entry / reflection after watching Synechdoche New York

Tonight I watched "Synecdoche, New York" again. This feeling was a sort of a priori for me, a feeling that has permeated: a double acting, or that I am the person acting as myself within a simulation of the real. Or as explained by Jean Baudrillard, that I am a hyperreal person based on distorted, controlled, and relearnt codes—a sort of Chinese whispers that distorts the real ever more from the conception of mankind. I watch this movie and realise again that I am forever alone, that we all are, as the moments to subdue the learnt and to feel the real are limited bursts that light me inside. And if I feel and see, it is but a simulation of that within itself. If we all know we are the main characters and we are hyperreal detached versions of the real, then what is after? What is the next realisation? Is there a next realisation?

Progress - With evidencer

Through the experimenting with AI and generating imagery through comfyUI I created this one piece that really stood out to me. Below is a diary entry based on this production.

DIARY - Troll Disk Sculpture


Thinking about a multi layered sort of ampiitheatrical discourse with multiple other dialogical circles and filter systems, with the person being the masses, the creator, the surveilled, the targetted and created by the mutilayers of media.

ComfyUI_00136_.png
IDEA - Laser Cut out the various rings. using thin ply at the school printer. then use cut up printed out bits of paper. Just make a small one, noone can tell the scale of a photo.

Maybe use spray paint for the black thin rings and can use like an epoxy resin over the whole piece and hac another piece of ply behind it that all the pieces are glued to.

Could use stencils and spray paint although could be difficult. benefit of cutting the wood up into the pieces though would be so that I can REDO the different parts, also the outer ring would be paper, glued onto the ply, exacto knife all around it and then finaly with some resin.

Could do this over the weekend or even like tomorrow